paper-with-me

홈 › Papers

Music Generation using Human-In-The-Loop Reinforcement Learning

2025-01-25 · Aju Ani Justus

This paper presents an approach that combines Human-In-The-Loop Reinforcement Learning (HITL RL) with principles derived from music theory to facilitate real-time generation of musical compositions. HITL RL, previously employed in diverse applications such as modelling humanoid robot mechanics and enhancing language models, harnesses human feedback to refine the training process. In this study, we develop a HILT RL framework that can leverage the constraints and principles in music theory. In particular, we propose an episodic tabular Q-learning algorithm with an epsilon-greedy exploration policy. The system generates musical tracks (compositions), continuously enhancing its quality through iterative human-in-the-loop feedback. The reward function for this process is the subjective musical taste of the user.

📄 PDF Abstract BibTeX arXiv:2501.15304

Code (0)

등록된 구현이 없습니다.

Tasks

Music GenerationQ-Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning

2020-02-08 · Nan Jiang, Sheng Jin, Zhiyao Duan, Chang-Shui Zhang

This paper presents a deep reinforcement learning algorithm for online accompaniment generation, with potential for real-time interactive human-machine duet improvisation. Different from offline music generation and harm…

Deep Reinforcement LearningMusic Generationreinforcement-learningReinforcement Learning+1

MusicRL: Aligning Music Generation to Human Preferences

2024-02-06 · Geoffrey Cideron, Sertan Girgin, Mauro Verzetti, Damien Vincent 외

We propose MusicRL, the first music generation system finetuned from human feedback. Appreciation of text-to-music models is particularly subjective since the concept of musicality as well as the specific intention behin…

Music Generation

NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms

2025-02-25 · Yashan Wang, Shangda Wu, Jianhuai Hu, Xingjian Du 외

We introduce NotaGen, a symbolic music generation model aiming to explore the potential of producing high-quality classical sheet music. Inspired by the success of Large Language Models (LLMs), NotaGen adopts pre-trainin…

Language ModelingLanguage ModellingLarge Language ModelMusic Generation+2

Live Music Models

2025-08-06 · Lyria Team, Antoine Caillon, Brian McWilliams, Cassie Tarakajian 외 arxiv

We introduce a new class of generative models for music called live music models that produce a continuous stream of music in real-time with synchronized user control. We release Magenta RealTime, an open-weights live mu…

Music Generation

Tidal MerzA: Combining affective modelling and autonomous code generation through Reinforcement Learning

2024-09-12 · Elizabeth Wilson, György Fazekas, Geraint Wiggins

This paper presents Tidal-MerzA, a novel system designed for collaborative performances between humans and a machine agent in the context of live coding, specifically focusing on the generation of musical patterns. Tidal…

Code GenerationMusic Generationreinforcement-learningReinforcement Learning